Model save

README.md

@@ -0,0 +1,85 @@
+---
+license: mit
+base_model: indolem/indobert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: sentiment-seq_bn-rf64-3
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sentiment-seq_bn-rf64-3
+
+This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3414
+- Accuracy: 0.8546
+- Precision: 0.8284
+- Recall: 0.8146
+- F1: 0.8210
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 30
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.5636        | 1.0   | 122  | 0.5152          | 0.7218   | 0.6550    | 0.6307 | 0.6380 |
+| 0.5068        | 2.0   | 244  | 0.4980          | 0.7318   | 0.6828    | 0.6953 | 0.6877 |
+| 0.4683        | 3.0   | 366  | 0.4659          | 0.7694   | 0.7222    | 0.7244 | 0.7232 |
+| 0.4465        | 4.0   | 488  | 0.4401          | 0.7895   | 0.7462    | 0.7385 | 0.7421 |
+| 0.4152        | 5.0   | 610  | 0.4214          | 0.8120   | 0.7729    | 0.7845 | 0.7781 |
+| 0.3848        | 6.0   | 732  | 0.4166          | 0.8321   | 0.7961    | 0.8187 | 0.8053 |
+| 0.3714        | 7.0   | 854  | 0.3987          | 0.8396   | 0.8206    | 0.7765 | 0.7932 |
+| 0.3529        | 8.0   | 976  | 0.3900          | 0.8421   | 0.8272    | 0.7758 | 0.7945 |
+| 0.3471        | 9.0   | 1098 | 0.3775          | 0.8521   | 0.8258    | 0.8104 | 0.8174 |
+| 0.3335        | 10.0  | 1220 | 0.3722          | 0.8596   | 0.8325    | 0.8257 | 0.8290 |
+| 0.3333        | 11.0  | 1342 | 0.3652          | 0.8546   | 0.8284    | 0.8146 | 0.8210 |
+| 0.3171        | 12.0  | 1464 | 0.3616          | 0.8521   | 0.8247    | 0.8129 | 0.8184 |
+| 0.2959        | 13.0  | 1586 | 0.3637          | 0.8571   | 0.8463    | 0.7964 | 0.8152 |
+| 0.3177        | 14.0  | 1708 | 0.3496          | 0.8622   | 0.8385    | 0.8225 | 0.8298 |
+| 0.2923        | 15.0  | 1830 | 0.3454          | 0.8596   | 0.8325    | 0.8257 | 0.8290 |
+| 0.2887        | 16.0  | 1952 | 0.3454          | 0.8596   | 0.8325    | 0.8257 | 0.8290 |
+| 0.2916        | 17.0  | 2074 | 0.3442          | 0.8596   | 0.8336    | 0.8232 | 0.8281 |
+| 0.2937        | 18.0  | 2196 | 0.3433          | 0.8596   | 0.8336    | 0.8232 | 0.8281 |
+| 0.2902        | 19.0  | 2318 | 0.3423          | 0.8521   | 0.8258    | 0.8104 | 0.8174 |
+| 0.2928        | 20.0  | 2440 | 0.3414          | 0.8546   | 0.8284    | 0.8146 | 0.8210 |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter-sentiment/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 64,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "config_id": "337ea3bbdc05e9b8",
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "indolem/indobert-base-uncased",
+  "model_type": "bert",
+  "name": "adapter-sentiment",
+  "version": "0.2.2"
+}

adapter-sentiment/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44ffde0ca1e8c9ef6a66b874a466c7ddf07f04e27701ad5223a069fe09a1e42a
+size 939494

default/head_config.json

@@ -0,0 +1,19 @@
+{
+  "config": {
+    "activation_function": "gelu",
+    "bias": true,
+    "embedding_size": 768,
+    "head_type": "masked_lm",
+    "label2id": null,
+    "layer_norm": true,
+    "layers": 2,
+    "shift_labels": false,
+    "vocab_size": 31923
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "indolem/indobert-base-uncased",
+  "model_type": "bert",
+  "name": "default",
+  "version": "0.2.2"
+}

default/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a181f0177f3154142b57d9cab72a7e6f72dea1fe172d1a480ff543e0c17b0f3f
+size 100566390

sentiment/head_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "0": 0,
+      "1": 1
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "indolem/indobert-base-uncased",
+  "model_type": "bert",
+  "name": "sentiment",
+  "version": "0.2.2"
+}

sentiment/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a757d4b2d7a40e3498e11ba8b50be8dc4aafa39a519891860d08c1767b79f2
+size 2370664